{
  "id": "2306.00979",
  "version": "v1",
  "published": "2023-06-01T17:59:21.000Z",
  "updated": "2023-06-01T17:59:21.000Z",
  "title": "Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds",
  "authors": [
    "Shaowei Liu",
    "Saurabh Gupta",
    "Shenlong Wang"
  ],
  "comment": "Accepted to CVPR 2023. Project page: https://stevenlsw.github.io/reart",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1 degree-of-freedom joints. Given point cloud videos of such everyday objects, our method identifies the distinct object parts, what parts are connected to what other parts, and the properties of the joints connecting each part pair. We do this by jointly optimizing the part segmentation, transformation, and kinematics using a novel energy minimization framework. Our inferred animatable models, enables retargeting to novel poses with sparse point correspondences guidance. We test our method on a new articulating robot dataset, and the Sapiens dataset with common daily objects, as well as real-world scans. Experiments show that our method outperforms two leading prior works on various metrics.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-06-01T17:59:21.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "4d point clouds",
      "arbitrary 3d objects",
      "building rearticulable models",
      "everyday man-made objects containing",
      "sparse point correspondences guidance"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}